This directory contains PyTorch YOLOv3 software developed by Ultralytics LLC, and is freely available for redistribution under the GPL-3.0 license. For more information please visit https://www.ultralytics.com.
- How to load your custom image detection data from Roboflow
- How to instatiate a pytorch YOLOv3 model
- How to train the YOLOv3 model
- How to use the trained model for quick inference
- How to save model weights for future use
- This blogpost provides a roadmap (though it is tailored to a keras implementation)
- This notebook provides the code necessary to run the tutorial
- For reading purposes, the notebook is also saved in Tutorial.ipynb
Roboflow makes managing, preprocessing, augmenting, and versioning datasets for computer vision seamless. Developers reduce 50% of their code when using Roboflow's workflow, automate annotation quality assurance, save training time, and increase model reproducibility.